Our papers (one regular paper and one short paper) have been accepted to the Pacific Rim International Conference on Artificial Intelligence (PRICAI 2025) (Wellington, New Zealand, November 17-21, 2025).

• Keisuke Sugawara, Kento Uchida, and Shinichi Shirakawa: Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift (Accepted as a Regular Paper)
• Daiki Yotsufuji, Kenta Nishihara, Shoma Shimizu, Kento Uchida, and Shinichi Shirakawa: OnDeFog: Online Decision Transformer under Frame Dropping (Accepted as a Short Paper)

Our paper has been accepted to the 51st Annual Conference of the IEEE Industrial Electronics Society (IECON 2025). This paper proposes uncertainty-aware self-localization for bulldozers based on machine learning. This work is a collaborative research with Komatsu Ltd.

• Hikaru Sawafuji, Ryota Ozaki, Takuto Motomura, Toyohisa Matsuda, Masanori Tojima, Kento Uchida, and Shinichi Shirakawa: Uncertainty-Aware Self-Localization for Bulldozers Using Machine Learning with Internal Sensor Data, The 51st Annual Conference of the IEEE Industrial Electronics Society (IECON 2025), Madrid, Spain, October 14-17, 2025. (Accepted)

We presented on surrogate benchmarks for model merging optimization at AutoML 2025 Non-Archival Content Track.

• Rio Akizuki, Yuya Kudo, Nozomu Yoshinari, Yoichi Hirose, Toshiyuki Nishimoto, Kento Uchida, and Shinichi Shirakawa: Surrogate Benchmarks for Model Merging Optimization, International Conference on Automated Machine Learning (AutoML 2025), Non-Archival Content Track, New York City, USA, September 8-11, 2025. [Link] [arXiv]

We presented on atherosclerosis risk prediction using large language models at ESC Congress 2025. This work is a joint research with Prof. Yano at Juntendo University, etc.

• Hibiki Murase, Kei Hiroshima, Kento Uchida, Mizuki Ohashi, Naoki Kashihara, Anthony Viera, Hiroyuki Daida, Shinichi Shirakawa, and Yuichiro Yano: Enhancing atherosclerosis risk prediction with strategic feature and case selections in large language model, ESC Congress 2025, Madrid, Spain, August 29 - September 1, 2025.

Our papers regarding prompt optimization in LLM have been accepted to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) as a Findings paper.

• Rin Ashizawa, Yoichi Hirose, Nozomu Yoshinari, Kento Uchida, and Shinichi Shirakawa: Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers, Findings of the Association for Computational Linguistics (ACL 2025 Findings), pp. 20799–20817, Vienna, Austria (hybrid), July 27 - August 1, 2025. [DOI] [arXiv] [Code]

Our papers (three full papers and two poster paper) have been accepted to Genetic and Evolutionary Computation Conference (GECCO) 2025 (Málaga, Spain (hybrid), July 14-18, 2025).

Members’ Page has been updated. Now, our laboratory has 10 doctoral course students, 15 master’s course students, and 5 undergraduate students for graduation research.

Our paper has been accepted to the Workshop on Ubiquitous Network Intelligence for Next Generation Wireless Networks in IEEE GLOBECOM 2024). This work is collaborative research with Prof. Nishio at Tokyo Institute of Technology. This paper proposes neural architectures with vector quantized bottlenecks for split inference to reduce the traffic between edge devices and servers.

Our paper has been accepted to 31st International Conference on Neural Information Processing (ICONIP 2024). This paper proposes an adaptation method of trust region for trust region policy optimization (TRPO).

• Shoma Shimizu, Kento Uchida, Atsuo Maki, and Shinichi Shirakawa: Adaptive Trust Region Radius for Robust Policy Optimization, 31st International Conference on Neural Information Processing (ICONIP 2024), Auckland, New Zealand, December 2-6, 2024.

Our paper regarding theoretical analysis for the categorical version of the compact genetic algorithm has been accepted to Evolutionary Computation (MIT Press). This work is collaborative research with Prof. Akimoto (University of Tsukuba), etc.

• Ryoki Hamano, Kento Uchida, Shinichi Shirakawa, Daiki Morinaga, and Youhei Akimoto: Tail Bounds on the Runtime of Categorical Compact Genetic Algorithm, Evolutionary Computation, (Accepted) [DOI] [arXiv]